Files
2026-09-04 16:30:37 +08:00

48 lines
1.7 KiB
YAML

groups:
- name: node-basic-alerts
rules:
- alert: NodeExporterDown
expr: up{job="node"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "节点采集器离线"
description: "{{ $labels.instance }} node-exporter 已超过 1 分钟不可用。"
- alert: RabbitMQMetricsDown
expr: up{job="rabbitmq"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "RabbitMQ 指标不可用"
description: "{{ $labels.instance }} Prometheus 指标端点已超过 1 分钟不可用。"
- alert: NodeHighCpuUsage
expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
for: 5m
labels:
severity: warning
annotations:
summary: "节点 CPU 使用率过高"
description: "{{ $labels.instance }} CPU 使用率持续 5 分钟超过 85%。"
- alert: NodeHighMemoryUsage
expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 85
for: 5m
labels:
severity: warning
annotations:
summary: "节点内存使用率过高"
description: "{{ $labels.instance }} 内存使用率持续 5 分钟超过 85%。"
- alert: NodeLowDiskSpace
expr: (1 - node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"}) * 100 > 85
for: 5m
labels:
severity: warning
annotations:
summary: "节点磁盘空间不足"
description: "{{ $labels.instance }} {{ $labels.mountpoint }} 磁盘使用率持续 5 分钟超过 85%。"